© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71243
    Prev
    Next
    INDEX
    Explanations

    explaining why or offering a description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    0.51
    unto
    0.43
     accompanied
    0.41
    財
    0.39
    伴
    0.39
     unim
    0.39
    英
    0.39
     acompañ
    0.38
     pharmaceutical
    0.38
     apni
    0.38
    POSITIVE LOGITS
    ˁ
    0.54
    getTag
    0.53
    urangan
    0.51
     숨
    0.51
    ansı
    0.51
     힘들
    0.50
    छात्रा
    0.49
     stanovnika
    0.49
     हीरे
    0.49
     인증
    0.49
    Activations Density 0.010%

    No Known Activations